Single Image Dehazing Based on Deep Neural Network

This paper proposes a single image dehazing based on deep neural network that is to deal with haze image. In this paper, we build up a deep neural network to restore the hazy image. We test our method both objective and subjective and compare with classical method for dehazing. Our test shows that our method works better than the others in reducing Halo effect and also our method does well in restore colorful of input image. Finally, our method process faster.

[1]  Jean-Philippe Tarel,et al.  Fast visibility restoration from a single color or gray level image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[2]  Mohinder Malhotra.  Single Image Haze Removal Using Dark Channel Prior , 2016 .

[3]  Robby T. Tan,et al.  Visibility in bad weather from a single image , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Raanan Fattal,et al.  Single image dehazing , 2008, ACM Trans. Graph..

[5]  Zia-ur Rahman,et al.  Multi-scale retinex for color image enhancement , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[6]  William J. Fitzgerald,et al.  An Alternative Algorithm for Adaptive Histogram Equalization , 1996, CVGIP Graph. Model. Image Process..

[7]  Jian Sun,et al.  Guided Image Filtering , 2010, ECCV.

[8]  Shree K. Nayar,et al.  Contrast Restoration of Weather Degraded Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Shree K. Nayar,et al.  Vision and the Atmosphere , 2002, International Journal of Computer Vision.

[10]  J. Alex Stark,et al.  Adaptive image contrast enhancement using generalizations of histogram equalization , 2000, IEEE Trans. Image Process..

[11]  Rob Fergus,et al.  Depth Map Prediction from a Single Image using a Multi-Scale Deep Network , 2014, NIPS.

[12]  Ling Shao,et al.  A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior , 2015, IEEE Transactions on Image Processing.